Sparse Representation Shape Models
Sparse Representation Shape Models
复制标题
稀疏表示形状模型
DOI:
10.1007/s10851-012-0394-3
复制
发表时间:
2010-12
影响因子:
2
通讯作者:
Jigang Wu
中科院分区:
文献类型:
--
作者:
Yuelong Li;Jufu Feng;Li Meng;Jigang Wu
It is well-known that, during shape extraction, enrolling an appropriate shape constraint model could effectively improve locating accuracy. In this paper, a novel deformable shape model, Sparse Representation Shape Models (SRSM), is introduced. Rather than following commonly utilized statistical shape constraints, our model constrains shape appearance based on a morphological structure, the convex hull of aligned training samples, i.e., only shapes that could be linearly represented by aligned training samples with the sum of coefficients equal to one, are defined as qualified. This restriction strictly controls shape deformation modes to reduce extraction errors and prevent extremely poor outputs. This model is realized based on sparse representation, which ensures during shape regularization the maximum valuable shape information could be reserved. Besides, SRSM is interpretable and hence helpful to further understanding applications, such as face pose recognition. The effectiveness of SRSM is verified on two publicly available face image datasets, the FGNET and the FERET.
登录
查看更多内容
影响因子:
3.3
作者:
Søren G. H. Erbou;Martin Vester-Christensen;R. Larsen;L. B. Christensen;B. Ersbøll
通讯作者:
Søren G. H. Erbou;Martin Vester-Christensen;R. Larsen;L. B. Christensen;B. Ersbøll
DOI:
10.1109/iccv.1999.790376
发表时间:
1999-09
期刊:
Proceedings of the Seventh IEEE International Conference on Computer Vision
影响因子:
--
作者:
S. Li;Juwei Lu
通讯作者:
S. Li;Juwei Lu
DOI:
10.1007/bfb0015522
发表时间:
1996-04
期刊:
--
影响因子:
--
作者:
P. Belhumeur;J. Hespanha;D. Kriegman
通讯作者:
P. Belhumeur;J. Hespanha;D. Kriegman
DOI:
--
发表时间:
1999
期刊:
--
影响因子:
--
作者:
Tim Cootes;C. Taylor
通讯作者:
Tim Cootes;C. Taylor
DOI:
--
发表时间:
2005
期刊:
--
影响因子:
--
作者:
D. Donoho
通讯作者:
D. Donoho